Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    force multiplied by time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いき
    0.64
    二
    0.61
    प
    0.57
    你的
    0.57
     increments
    0.57
    भ
    0.57
    ⿴
    0.57
    ный
    0.56
    ています
    0.55
     craindre
    0.55
    POSITIVE LOGITS
     gerais
    0.96
     PFAS
    0.93
     Holiness
    0.91
     DeFi
    0.88
     आल्सो
    0.88
     PKD
    0.87
     generales
    0.86
     Deloitte
    0.86
     AISI
    0.86
    ச்சா
    0.85
    Act Density 0.000%

    No Known Activations